# llama.cpp release b11322 adds macOS and Linux binaries

> The open‑source LLM runtime posted new pre‑built binaries for macOS, iOS and several Ubuntu variants on Oct 1 2026.

Oossa · 2026-10-01 · https://oossa.com/en/llama-cpp-release-b11322-adds-macos-and-linux-binaries

The ggml‑org team released version b11322 of llama.cpp on Oct 1 2026. The update bundles pre‑compiled binaries for Apple Silicon macOS, Intel macOS, iOS, and multiple Ubuntu builds (CPU, Vulkan, CUDA). A race‑condition fix in the hex‑workqueue component is also included. The binaries are available as direct download links on the GitHub release page.

## The facts

- Release version b11322 published on 2026-10-01
- Provides binaries for macOS Apple Silicon, macOS Intel, iOS, Ubuntu x64 (CPU, Vulkan, CUDA), Ubuntu arm64, and Ubuntu s390x

## Why it matters

Developers can now run llama.cpp locally on more platforms without building from source, speeding up testing and deployment.

## Sources & references

1. [ggml-org/llama.cpp b11322](https://github.com/ggml-org/llama.cpp/releases/tag/b11322) – llama.cpp, 2026-10-01

Last updated: 2026-10-01